SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion

2026-03-11

AI Summary

This work proposes SNPgen, a two-stage conditional latent diffusion framework for synthesizing genotype data aligned with phenotypic outcomes. Existing methods typically generate genotypes unconditionally, limiting their utility in downstream tasks due to poor phenotype alignment. SNPgen first identifies key SNPs guided by genome-wide association studies (GWAS), then compresses genotypes using a variational autoencoder and employs a classifier-free guidance diffusion model in the latent space to generate high-fidelity synthetic genotypes conditioned on binary disease labels. Evaluated on four complex diseases from the UK Biobank using only 1,024–2,048 SNPs, models trained on synthetic data achieve performance on real test sets comparable to polygenic risk scores derived from the full genome. Privacy assessments confirm no identity leakage, while genetic structure is well preserved—demonstrating, for the first time, phenotype-supervised genotype synthesis that balances utility and privacy.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Privacy
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Security and Privacy: Data transparency and provenance
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Polygenic risk scores and other genomic analyses require large individual-level genotype datasets, yet strict data access restrictions impede sharing. Synthetic genotype generation offers a privacy-preserving alternative, but most existing methods operate unconditionally, producing samples without phenotype alignment, or rely on unsupervised compression, creating a gap between statistical fidelity and downstream task utility. We present SNPgen, a two-stage conditional latent diffusion framework for generating phenotype-supervised synthetic genotypes. SNPgen combines GWAS-guided variant selection (1,024-2,048 trait-associated SNPs) with a variational autoencoder for genotype compression and a latent diffusion model conditioned on binary disease labels via classifier-free guidance. Evaluated on 458,724 UK Biobank individuals across four complex diseases (coronary artery disease, breast cancer, type 1 and type 2 diabetes), models trained on synthetic data matched real-data predictive performance in a train-on-synthetic, test-on-real protocol, approaching genome-wide PRS methods that use $2$-$6\times$ more variants. Privacy analysis confirmed zero identical matches, near-random membership inference (AUC $\approx 0.50$), preserved linkage disequilibrium structure, and high allele frequency correlation ($r \geq 0.95$) with source data. A controlled simulation with known causal effects verified faithful recovery of the imposed genetic association structure.

Problem

• synthetic genotype generation
• phenotype alignment
• data privacy
• polygenic risk scores
• genomic data sharing

Innovation

• conditional latent diffusion
• phenotype-supervised generation
• synthetic genotypes
• GWAS-guided SNP selection
• privacy-preserving genomic data